Browse Articles
Discover research articles across all indexed journals
Facial Recognition in Smart Devices: Enhancing Security and Convenience
Facial recognition technology (FRT) has become an essential component of modern security and convenience, integrating biometrics with advanced artificial intelligence (AI) techniques. This technology enables accurate identification and verification of individuals by analyzing facial characteristics, making it widely applicable in access control, security monitoring, and time attendance systems. The evolution of FRT dates back to the 1960s, progressing from manual facial measurements to deep learning-based algorithms utilizing convolutional neural networks (CNNs). Recent advancements, including 3D facial recognition, infrared imaging, and edge computing, have significantly improved accuracy, efficiency, and security against spoofing attacks. Today, facial recognition is incorporated into various smart devices, such as mobile phones and laptops, ensuring enhanced privacy and safety. The increasing adoption of facial biometrics has revolutionized digital security, offering seamless authentication methods for personal and enterprise applications. This paper explores the development, applications, and future potential of facial recognition technology in smart devices.
Analysis of Diabetes Prediction using Decision Tree Classifier
Diabetes is a serious complaint that affects the maturity of the population. Now a days its play a major role on human life. Imbalance in insulin processing by the body which leads to varieties of disorder. The main aim of this work is to make an early prediction of diabetes more precisely by using Auto Machine Learning Tools. Auto Machine learning Tools provide better results in diabetes detection by constructing models from patient datasets. This model automates the training, tuning, and deploying machine learning models. Recent developments in Machine learning show that Automatic Diabetic detection using Random Forest Algorithm models can be very beneficial in such problems. The proposed Random forest model predicts the diabetes at early stage. We use Decision tree classifier to predict whether a patient has diabetes based on diagnostic measurements. Performance and accuracy of the applied algorithm is discusses and compared.
Analysis of CBC and CRP for Children using Machine Learning Models
Complete Blood count (CBC) and C- Reactive Protein (CRP) tests provide valuable information about a child's health status and help healthcare providers to diagnose and manage various medical conditions effectively. Paediatric health assessment often relies on these two critical blood tests as normal reports to check the primary condition of the children. Integration of CRP prediction models into clinical decision support systems can facilitate early detection of inflammatory conditions, guide treatment strategies, and improve patient outcomes in paediatric populations. Machine Learning (ML) algorithms are used to enhance diagnostic accuracy, and improve the overall efficiency of paediatric care. The most important test for diagnosing infections is the CBC. The CRP readings are classified into three classes i.e., 0 to 3 mg/L, 3 mg/L to 20 mg/L, more than 20 mg/L. With the test reports of the CBC, prediction of CRP levels was found with highest accuracy from Cat Boosting Classifier [0.976], Neural Network [0.972], Logistic Regression [0.971] and Random Forest Classifier [0.966]. The results prove that the Cat Boosting Classifier performs best among all the used models followed by other algorithms and performs well in predicting the new CRP reading class in all the prediction scenarios given the available dataset. Automating the analysis of CBC and CRP tests can streamline healthcare processes using ML models.
Techniques to Predict Employee Attrition Using Optimized Levy Fruit Fly Optimization Algorithm
Competent people are a valuable asset for strong businesses. The issue of retaining competent staff with expertise poses a challenge to business owners. Employee attrition may be costly for businesses since it takes a lot to compensate for their experience and efficiency. As a result, this study proposes a novel model for predicting employee attrition utilizing machine learning techniques. The datasets are collected from Kaggle resource. The dataset has been pre-processed using standard scalar with Label Encoding method. The dataset has been trained with ML algorithm. The best features are selected by using modified genetic algorithm (MGA). The classification has been done with KNN, Gradient Boosting and Extra tree classifier. Finally, the attrition prediction using optimized levy fruit fly optimization (OLFFO). The experimental results are compared with ML algorithms with classification metrics (Accuracy, Precision, recall and f-measure).
Denim Fabric: Construction, Thermophysiological Comfort and Future Trends
Denim fabric is widely used in fashion, known for its durability, versatility, and style. However, its effect on thermophysiological comfort, particularly in a variety of environmental situations, remains a source of curiosity and research. This review focuses at the intricate relationship between denim fabric structure and thermophysiological comfort, which include data from current studies in textile science, ergonomics, and apparel development. Fibre type, yarn structure, fabric weight, weave pattern, and finishing treatments are studied in terms of heat regulation, moisture management, breathability, and overall wear comfort. The effect of denim construction on physiological responses, such as skin temperature, moisture retention, and subjective comfort, is explored in a variety of climatic and activity settings. Furthermore, advances in textile technology and novel techniques to improving denim comfort qualities are studied. This paper aims to provide insights on optimizing denim fabric construction for increased thermophysiological comfort, to help to the development of more comfortable and functional denim apparel.
Unleashing the Power of Serverless Architectures in Cloud Technology: A Comprehensive Analysis and Future Trends
This research paper delves into the transformative impact of serverless architectures on cloud technology adoption, emphasizing improved scalability, cost-efficiency, and agility. Using a quantitative approach with a survey of 300 organizations, the findings reveal a significant 25% reduction in infrastructure costs for those fully embracing serverless computing compared to traditional cloud architectures. Additionally, serverless adopters experience a noteworthy 30% increase in scalability and a remarkable 15% reduction in time-to-market for new applications, highlighting the agility and rapid development capabilities associated with this paradigm. The study also addresses security concerns, indicating a 10% reduction in security incidents for organizations with robust serverless security practices. These quantitative results provide empirical evidence and valuable insights for businesses aiming to optimize their cloud technology strategies and leverage the tangible benefits of serverless architectures.
Automating Grievance Portal by Automating Central Grievance Redressal System using Artificial Intelligence
This research paper is introduces as a centralized grievance portal based on Artificial Intelligence (AI) for streamlined and effective complaint resolution. The proposed system manipulates advanced AI techniques to enhance the complaint handling process, providing a user-friendly interface for complainants & optimizing resource utilization for resolution authorities. The integration of machine learning algorithms ensures intelligent analysis of complaints, prioritization, and swift solution, ultimately contributing to an efficient and transparent grievance redressal mechanism
A Comprehensive Study on Image Classification Using Deep Learning Techniques
In recent years, the field of computer vision has witnessed significant advancements, particularly in image classification, owing to the remarkable progress in deep learning techniques. This research paper presents a comprehensive study on image classification using CNN deep learning models, exploring the evolution of methodologies, state-of-the-art architectures, challenges, and potential applications. The primary objective is to analyse the effectiveness of deep learning in image classification tasks and provide insights into the current trends and future directions in this rapidly evolving domain.
A Data-Infused Approach to optimal Paying Guest / Hostel Selections
The world's population is expanding quickly every day, and a great number of individuals are moving to big cities and other locations in search of employment, better living conditions, or educational opportunities. The development of rental websites is covered in this paper. Property details can be uploaded by landlords and tenants can rent properties through this website. In this research, we have developed website will assist people in giving or accepting rental properties without the need to interact with apartment brokers in order to ultimately come to a mutually beneficial agreement. Among the one hundred different options, the project's goal is to identify and suggest the PG that a user is most likely to book.
Implementation of Smart Hindrance Tracking System
The Smart Hindrance Tracking System for Blind Individuals is a mini-project aimed at enhancing the mobility and safety of visually impaired individuals in navigating their surroundings. Leveraging cutting-edge technologies, this system integrates computer vision, sensor networks, and mobile applications to provide real-time hindrance detection and navigation assistance. The primary objective is to empower blind individuals with a reliable and intelligent solution that enables them to identify and navigate around obstacles in their path. The system utilizes a combination of depth-sensing cameras and ultrasonic sensors to detect obstacles in the user's vicinity. These sensors feed data to a central processing unit, where a computer vision algorithm processes the information in real-time, identifying obstacles and their spatial locations. The processed data is then communicated to the user through a user-friendly mobile application. This research presents the daily challenges faced by visually impaired individuals but also fosters inclusivity and independence. The Smart Hindrance Tracking System stands at the intersection of technology and social impact, offering an innovative solution to improve the lives of those with visual impairments.
Smart Emotion Detector by Using Python
The capability to perceive and comprehend human emotions holds significant importance across diverse realms of human interaction, ranging from enhancing human- computer interfaces to assisting in mental health diagnosis. This study presents an innovative Smart Emotion Detector, a resilient system engineered to precisely recognize and categorize facial human expression time. Face Detection entails the system's ability to identify human faces captured by the camera. In this context, we implement a digital attendance management system for classroom students utilizing facial recognition techniques.
Automatic Parking Management System and Parking Fee Collection Based on Number Plate Recognition
This research paper dives into the complexities of a programmed stopping framework and electronic stopping expense assortment, principally founded on vehicle number plate acknowledgment. The essential goal is to plan and carry out a programmed stopping framework that essentially improves the accommodation and security of public parking areas. Additionally, it aims to facilitate parking fee collection without the complexities associated with magnetic cards. The proposed automatic parking system boasts several key features. First and foremost, it minimizes human interaction by eliminating the need for magnetic cards and associated devices. Users can seamlessly enter and exit parking lots without physical tokens, enhancing overall convenience. Furthermore, the system incorporates a parking guidance feature that directs users to available parking spaces. Real-time information about vacant spots ensures efficient utilization of parking areas. The heart of the system lies in its number plate recognition capabilities. The significance of this research extends beyond parking management. It contributes to ongoing efforts to automate and digitize essential services, making them more accessible and user-friendly. By embracing such technological advancements, cities can enhance user experiences, improve efficiency, and pave the way for a future of automated systems in public services.
A Data-Infused Approach to Optimal PG / Hostel Selections
The world's population is expanding quickly every day, and a great number of individuals are moving to big cities and other locations in search of employment, better living conditions, or educational opportunities. That is why house renting is becoming an essential part of our society due to the increase in housing demand. Subsequently, I understood the significance of a web based house leasing site and thought of a choice to execute such a web application. The development of rental websites is covered in this paper. Property details can be uploaded by landlords and tenants can rent properties through this website. This website will assist people in giving or accepting rental properties without the need to interact with apartment brokers in order to ultimately come to a mutually beneficial agreement. Among the one hundred different options, the project's goal is to identify and suggest the PG that a user is most likely to book.
E-Learning Model based on Teaching and Learning Process
This model explores an e-learning module centered on enhancing the teaching and learning process. The module integrates interactive multimedia elements, adaptive assessments, and collaborative platforms to create an engaging virtual learning environment. The electronic delivery of education through various internet-based multimedia platforms and technologies is referred to as e-learning. The term "e-learning" describes the electronic delivery of education using a range of internet-based and multimedia platforms and tools. Selecting what to learn, how to learn it, when to learn it, and where to study it are all options available to the student while using e-learning modules. Online materials used for education, usually for remote learning or online learning, are called e-learning modules. They can also be used as stand-alone resources or as part of a higher program or course. Trying alternative assignments, such as, through blogs. Activating learning in groups as well as self-learning or self-reading.
Review on Computer Vision Techniques to enhance Road Lane Detection by using Open CV
In response to the alarming increase in road accidents attributed to driver inattention, recent advancements in road safety technology have become imperative. Addressing this concern, Lane Detection Systems have emerged as a pivotal component in technologically advanced transportation systems. These systems function by identifying lane boundaries on the road and promptly alerting the driver if there is deviation from correct lane markings. However, achieving robust lane detection poses challenges due to diverse road conditions encountered during driving, including night time and day time scenarios. This research focuses on a Lane Detection System that employs a front-facing camera to capture the road view and identify lane boundaries. The proposed method involves dividing the video image. This research presents the study explores various techniques for detecting lane markings, series of sub-images, extracting image features for each segment, and utilizing these features to recognize lanes on the road, acknowledging the complexity introduced by different driving conditions.
Optimization of Photovoltaic Capacity and Electric Vehicle Battery Charging at Electric Vehicle Charging Stations Using Particle Swarm Optimization
The transportation sector is one of the largest producers of carbon gas emissions. This encouraging electrification to reduce the impact of environmental damage. However, the impact of large-scale electrification causes an increase in peak load demand on the distribution network. This results in an energy crisis, economic losses, and reduces the reliability of the power system if not handled seriously. Important solutions involve optimizing electric vehicle charging stations (EVCS), accelerating the use of renewable energy for transportation and controlling electric vehicle charging. The hybrid microgrid system at EVCS can be an effective solution. This system is able to manage its own electricity needs through an energy management system with a combination of energy sources. This research discusses optimizing photovoltaic capacity and charging electric vehicle batteries at EVCS using particle swarm optimization (PSO). The aim of this research is to increase efficiency in investment and increase profits. The model is determined as an EVCS that is interconnected with photovoltaic (PV). The parameters determined include: charging load data, investment costs, power import tariff provisions and charging rates. PSO is used to size photovoltaic (PV) and battery energy storage systems (BESS). The results show that PSO can be used for optimization. This is proven by obtaining the position of the combination of PV and BESS with the best profit with a combination of PV of 494 kW and BESS of 581 kW, with an NPV of $1,652,604.89, an IRR of 46.60%, and a payback period of 2.15 years. The combination with the best PV contribution, namely PV of 3,146 kW and BESS of 1,811 kW, produces energy of 75,504 kWh per month, power import of 35,946 kWh and battery usage level of 58%. These two combinations of optimization results meet the investment acceptance requirements with an internal rate of return (IRR) of at least 9%.
Facial Recognition System with Attendance Tracking Using Python and Open CV
In educational institutions, businesses, and offices, attendance tracking stands as a crucial daily task. Traditionally performed manually, be it through name calling or roll numbers, there is a need for a more efficient solution. This project aims to revolutionize attendance management by implementing a Face Recognition-based system. Installed in classrooms, the system captures student details like name, roll number, class, section, and photographs, utilizing OpenCV for image extraction. As students approach the device, it takes and compares pictures with a trained dataset. The process involves face identification with a Haar cascade classifier, recognition using LBPH and automatic attendance labeling. An Excel sheet is generated and updated hourly, incorporating information from the class instructor. This approach aligns with the demand for modernization and efficient time management in attendance procedures.
Phytochemical screening and evaluation of the anti-venom effect of leaves extracts of Vitex negundo
The number of snake envenomation cases is estimated to be more than 5 million per year. Out of these cases, approximately 1,00,000 individuals experience severe complications. The objective of the current research is to investigate the effectiveness of local plant extracts from the western ghats of India in countering snake venom. The medicinal plant Vitex negundo has been traditionally used by healers in India to treat snakebite victims. Prior to injection, extract from the Vitex negundo plant was incubated at 37°C for 30 minutes. The study revealed that doses ranging from 0.15-0.17 mg of Vitex negundo extracts completely neutralized the lethal effects of V. russelli venom, while doses of 0.16-0.19 mg neutralized the lethal effects of Najanaja venom. In rats, the minimum edematic dose of the venom was found to be 4μg. Notably, significant inflammation was observed 1 hour after venom injection, with maximum inflammation occurring at 180 minutes. Furthermore, plant extracts administered at doses of 100mg/kg, 200mg/kg, and 400mg/kg exhibited significant activity compared to the control group. The minimum percentage inhibition was 29.13% and 27.1% at 100mg/kg, 58.18% and 57.21% at 240 minutes for 400mg/kg, and 60.89% for Vitex negundo with standard polyvalent antivenom. against V. Russelli and Najanaja venom, respectively.
RHEUMATIOD ARTHRITIS
Rheumatoid arthritis (RA) is a chronic autoimmune disease affecting joints, with risk factors including age, gender, genetics, and environmental exposures. Complications, such as joint damage, rheumatoid vasculitis, and Felty syndrome, underscore the need for effective management. Treatment modalities, ranging from Disease-Modifying Antirheumatic Drugs (DMARDs) to physical therapy and surgery, aim to alleviate symptoms and prevent further damage. While there is no cure for RA, ongoing research explores emerging therapies and precision medicine approaches. A multidisciplinary approach is crucial, tailoring treatment to individual needs for optimal outcomes and improved quality of life. Regular monitoring and adjustments to the treatment plan are essential aspects of RA management.
Lung Function Monitoring Using Machine Learning
This project aims to develop a system equipped with machine learning algorithm capable of continuously monitoring respiratory conduct. The system utilizes machine learning to interpret pulmonary function tests, lift the management of respiratory diseases, and potentially deliver improvements in the diagnosis and treatment of various disease states in pulmonary and critical care medicine. Additionally, the system automatically predicts lung function based on acoustic signals from coughing and wheezing, enabling noninvasive monitoring of asthma severity. The project also seeks to forecast lung age and improve the current dataset of audio samples to enhance the accuracy and reliability of the results. The application of machine learning in pulmonary function testing holds significant potential for remote monitoring of high risk patients and the early detection and treatment of lung diseases.